Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Olivier Siohan
@inproceedings{DBLP:conf/iclr/ChangHS23, author = {Oscar Chang and Dongseong Hwang and Olivier Siohan}, title = {Revisiting the Entropy Semiring for Neural Speech Recognition}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/pdf?id=SNgLnzFQeiD}, timestamp = {Fri, 30 Jun 2023 14:38:38 +0200}, biburl = {https://dblp.org/rec/conf/iclr/ChangHS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-10915, author = {Oscar Chang and Hank Liao and Dmitriy Serdyuk and Ankit Parag Shah and Olivier Siohan}, title = {Conformers are All You Need for Visual Speech Recogntion}, journal = {CoRR}, volume = {abs/2302.10915}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.10915}, doi = {10.48550/ARXIV.2302.10915}, eprinttype = {arXiv}, eprint = {2302.10915}, timestamp = {Tue, 09 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-10915.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-16398, author = {Richard Rose and Oscar Chang and Olivier Siohan}, title = {Cascaded encoders for fine-tuning {ASR} models on overlapped speech}, journal = {CoRR}, volume = {abs/2306.16398}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.16398}, doi = {10.48550/ARXIV.2306.16398}, eprinttype = {arXiv}, eprint = {2306.16398}, timestamp = {Mon, 03 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-16398.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-09369, author = {Avner May and Dmitriy Serdyuk and Ankit Parag Shah and Otavio Braga and Olivier Siohan}, title = {Audio-visual fine-tuning of audio-only {ASR} models}, journal = {CoRR}, volume = {abs/2312.09369}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.09369}, doi = {10.48550/ARXIV.2312.09369}, eprinttype = {arXiv}, eprint = {2312.09369}, timestamp = {Tue, 09 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-09369.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-10087, author = {Oscar Chang and Dongseong Hwang and Olivier Siohan}, title = {Revisiting the Entropy Semiring for Neural Speech Recognition}, journal = {CoRR}, volume = {abs/2312.10087}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.10087}, doi = {10.48550/ARXIV.2312.10087}, eprinttype = {arXiv}, eprint = {2312.10087}, timestamp = {Tue, 09 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-10087.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-10088, author = {Oscar Chang and Otavio Braga and Hank Liao and Dmitriy Serdyuk and Olivier Siohan}, title = {On Robustness to Missing Video for Audiovisual Speech Recognition}, journal = {CoRR}, volume = {abs/2312.10088}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.10088}, doi = {10.48550/ARXIV.2312.10088}, eprinttype = {arXiv}, eprint = {2312.10088}, timestamp = {Tue, 09 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-10088.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tmlr/ChangBLSS22, author = {Oscar Chang and Otavio Braga and Hank Liao and Dmitriy Serdyuk and Olivier Siohan}, title = {On Robustness to Missing Video for Audiovisual Speech Recognition}, journal = {Trans. Mach. Learn. Res.}, volume = {2022}, year = {2022}, url = {https://openreview.net/forum?id=fXorxxbDvO}, timestamp = {Fri, 19 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tmlr/ChangBLSS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/BragaS22, author = {Otavio Braga and Olivier Siohan}, title = {Best of Both Worlds: Multi-Task Audio-Visual Automatic Speech Recognition and Active Speaker Detection}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6047--6051}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746036}, doi = {10.1109/ICASSP43922.2022.9746036}, timestamp = {Tue, 07 Jun 2022 17:34:47 +0200}, biburl = {https://dblp.org/rec/conf/icassp/BragaS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RoseS22, author = {Richard Rose and Olivier Siohan}, editor = {Hanseok Ko and John H. L. Hansen}, title = {End-to-End multi-talker audio-visual {ASR} using an active speaker attention module}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2828--2832}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10866}, doi = {10.21437/INTERSPEECH.2022-10866}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/RoseS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SerdyukBS22, author = {Dmitriy Serdyuk and Otavio Braga and Olivier Siohan}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2833--2837}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10920}, doi = {10.21437/INTERSPEECH.2022-10920}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SerdyukBS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-10439, author = {Dmitriy Serdyuk and Otavio Braga and Olivier Siohan}, title = {Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition}, journal = {CoRR}, volume = {abs/2201.10439}, year = {2022}, url = {https://arxiv.org/abs/2201.10439}, eprinttype = {arXiv}, eprint = {2201.10439}, timestamp = {Tue, 01 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-10439.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-00652, author = {Richard Rose and Olivier Siohan}, title = {End-to-end multi-talker audio-visual {ASR} using an active speaker attention module}, journal = {CoRR}, volume = {abs/2204.00652}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.00652}, doi = {10.48550/ARXIV.2204.00652}, eprinttype = {arXiv}, eprint = {2204.00652}, timestamp = {Wed, 06 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-00652.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-05206, author = {Otavio Braga and Olivier Siohan}, title = {Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection}, journal = {CoRR}, volume = {abs/2205.05206}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.05206}, doi = {10.48550/ARXIV.2205.05206}, eprinttype = {arXiv}, eprint = {2205.05206}, timestamp = {Wed, 18 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-05206.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-05586, author = {Otavio Braga and Takaki Makino and Olivier Siohan and Hank Liao}, title = {End-to-End Multi-Person Audio/Visual Automatic Speech Recognition}, journal = {CoRR}, volume = {abs/2205.05586}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.05586}, doi = {10.48550/ARXIV.2205.05586}, eprinttype = {arXiv}, eprint = {2205.05586}, timestamp = {Wed, 18 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-05586.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-05684, author = {Otavio Braga and Olivier Siohan}, title = {A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection}, journal = {CoRR}, volume = {abs/2205.05684}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.05684}, doi = {10.48550/ARXIV.2205.05684}, eprinttype = {arXiv}, eprint = {2205.05684}, timestamp = {Wed, 18 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-05684.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/SerdyukBS21, author = {Dmitriy Serdyuk and Otavio Braga and Olivier Siohan}, title = {Audio-Visual Speech Recognition is Worth {\textdollar}32{\textbackslash}times 32{\textbackslash}times 8{\textdollar} Voxels}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2021, Cartagena, Colombia, December 13-17, 2021}, pages = {796--802}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ASRU51503.2021.9688191}, doi = {10.1109/ASRU51503.2021.9688191}, timestamp = {Wed, 09 Feb 2022 09:03:03 +0100}, biburl = {https://dblp.org/rec/conf/asru/SerdyukBS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/SachdevaMS21, author = {Kishan Sachdeva and Joshua Maynez and Olivier Siohan}, title = {Action Item Detection in Meetings Using Pretrained Transformers}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2021, Cartagena, Colombia, December 13-17, 2021}, pages = {861--868}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ASRU51503.2021.9688167}, doi = {10.1109/ASRU51503.2021.9688167}, timestamp = {Wed, 09 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/SachdevaMS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/BragaS21, author = {Otavio Braga and Olivier Siohan}, title = {A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6863--6867}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414160}, doi = {10.1109/ICASSP39728.2021.9414160}, timestamp = {Fri, 09 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/BragaS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DoutreHCPSC21, author = {Thibault Doutre and Wei Han and Chung{-}Cheng Chiu and Ruoming Pang and Olivier Siohan and Liangliang Cao}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Bridging the Gap Between Streaming and Non-Streaming {ASR} Systems by Distilling Ensembles of {CTC} and {RNN-T} Models}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {1807--1811}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-637}, doi = {10.21437/INTERSPEECH.2021-637}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DoutreHCPSC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RoseSTB21, author = {Richard Rose and Olivier Siohan and Anshuman Tripathi and Otavio Braga}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {End-to-End Audio-Visual Speech Recognition for Overlapping Speech}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {3016--3020}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-1621}, doi = {10.21437/INTERSPEECH.2021-1621}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/RoseSTB21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-14346, author = {Thibault Doutre and Wei Han and Chung{-}Cheng Chiu and Ruoming Pang and Olivier Siohan and Liangliang Cao}, title = {Bridging the gap between streaming and non-streaming {ASR} systems bydistilling ensembles of {CTC} and {RNN-T} models}, journal = {CoRR}, volume = {abs/2104.14346}, year = {2021}, url = {https://arxiv.org/abs/2104.14346}, eprinttype = {arXiv}, eprint = {2104.14346}, timestamp = {Tue, 04 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-14346.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2109-09536, author = {Dmitriy Serdyuk and Otavio Braga and Olivier Siohan}, title = {Audio-Visual Speech Recognition is Worth 32{\texttimes}32{\texttimes}8 Voxels}, journal = {CoRR}, volume = {abs/2109.09536}, year = {2021}, url = {https://arxiv.org/abs/2109.09536}, eprinttype = {arXiv}, eprint = {2109.09536}, timestamp = {Mon, 27 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2109-09536.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/BragaMSL20, author = {Otavio Braga and Takaki Makino and Olivier Siohan and Hank Liao}, title = {End-to-End Multi-Person Audio/Visual Automatic Speech Recognition}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {6994--6998}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053974}, doi = {10.1109/ICASSP40776.2020.9053974}, timestamp = {Thu, 23 Jul 2020 16:19:28 +0200}, biburl = {https://dblp.org/rec/conf/icassp/BragaMSL20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/MakinoLASGBS19, author = {Takaki Makino and Hank Liao and Yannis M. Assael and Brendan Shillingford and Basilio Garcia and Otavio Braga and Olivier Siohan}, title = {Recurrent Neural Network Transducer for Audio-Visual Speech Recognition}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019}, pages = {905--912}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ASRU46091.2019.9004036}, doi = {10.1109/ASRU46091.2019.9004036}, timestamp = {Mon, 24 Feb 2020 17:51:31 +0100}, biburl = {https://dblp.org/rec/conf/asru/MakinoLASGBS19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-04890, author = {Takaki Makino and Hank Liao and Yannis M. Assael and Brendan Shillingford and Basilio Garcia and Otavio Braga and Olivier Siohan}, title = {Recurrent Neural Network Transducer for Audio-Visual Speech Recognition}, journal = {CoRR}, volume = {abs/1911.04890}, year = {2019}, url = {http://arxiv.org/abs/1911.04890}, eprinttype = {arXiv}, eprint = {1911.04890}, timestamp = {Wed, 04 Dec 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-04890.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiSNCBMSSPCSWWV17, author = {Bo Li and Tara N. Sainath and Arun Narayanan and Joe Caroselli and Michiel Bacchiani and Ananya Misra and Izhak Shafran and Hasim Sak and Golan Pundak and Kean K. Chin and Khe Chai Sim and Ron J. Weiss and Kevin W. Wilson and Ehsan Variani and Chanwoo Kim and Olivier Siohan and Mitchel Weintraub and Erik McDermott and Richard Rose and Matt Shannon}, editor = {Francisco Lacerda}, title = {Acoustic Modeling for Google Home}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {399--403}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-234}, doi = {10.21437/INTERSPEECH.2017-234}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiSNCBMSSPCSWWV17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/Siohan17, author = {Olivier Siohan}, editor = {Francisco Lacerda}, title = {{CTC} Training of Multi-Phone Acoustic Models for Speech Recognition}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {709--713}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-505}, doi = {10.21437/INTERSPEECH.2017-505}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/Siohan17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SainathPSN17, author = {Tara N. Sainath and Vijayaditya Peddinti and Olivier Siohan and Arun Narayanan}, editor = {Francisco Lacerda}, title = {Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {3542--3546}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-231}, doi = {10.21437/INTERSPEECH.2017-231}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SainathPSN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Siohan16, author = {Olivier Siohan}, title = {Sequence training of multi-task acoustic models using meta-state labels}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {5425--5429}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472714}, doi = {10.1109/ICASSP.2016.7472714}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/Siohan16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SotoSEM16, author = {Victor Soto and Olivier Siohan and Mohamed Elfeky and Pedro J. Moreno}, title = {Selection and combination of hypotheses for dialectal speech recognition}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {5845--5849}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472798}, doi = {10.1109/ICASSP.2016.7472798}, timestamp = {Wed, 26 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SotoSEM16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/DoulatyRS16, author = {Mortaza Doulaty and Richard Rose and Olivier Siohan}, title = {Automatic optimization of data perturbation distributions for multi-style training in speech recognition}, booktitle = {2016 {IEEE} Spoken Language Technology Workshop, {SLT} 2016, San Diego, CA, USA, December 13-16, 2016}, pages = {21--27}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/SLT.2016.7846240}, doi = {10.1109/SLT.2016.7846240}, timestamp = {Wed, 16 Oct 2019 14:14:53 +0200}, biburl = {https://dblp.org/rec/conf/slt/DoulatyRS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/SiohanR15, author = {Olivier Siohan and David Rybach}, title = {Multitask learning and system combination for automatic speech recognition}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {589--595}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404849}, doi = {10.1109/ASRU.2015.7404849}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/asru/SiohanR15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuSSKL15, author = {Yanbo Xu and Olivier Siohan and David Simcha and Sanjiv Kumar and Hank Liao}, title = {Exemplar-based large vocabulary speech recognition using k-nearest neighbors}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5167--5171}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7178956}, doi = {10.1109/ICASSP.2015.7178956}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XuSSKL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiaoPSCCJSSBB15, author = {Hank Liao and Golan Pundak and Olivier Siohan and Melissa K. Carroll and Noah Coccaro and Qi{-}Ming Jiang and Tara N. Sainath and Andrew W. Senior and Fran{\c{c}}oise Beaufays and Michiel Bacchiani}, title = {Large vocabulary automatic speech recognition for children}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {1611--1615}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-373}, doi = {10.21437/INTERSPEECH.2015-373}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiaoPSCCJSSBB15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Siohan14, author = {Olivier Siohan}, title = {Training data selection based on context-dependent state matching}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {3316--3319}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6854214}, doi = {10.1109/ICASSP.2014.6854214}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/Siohan14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/KapralovaAWMS14, author = {Olga Kapralova and John Alex and Eugene Weinstein and Pedro J. Moreno and Olivier Siohan}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {A big data approach to acoustic model training corpus selection}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2083--2087}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-473}, doi = {10.21437/INTERSPEECH.2014-473}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/KapralovaAWMS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanB13, author = {Olivier Siohan and Michiel Bacchiani}, editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and Christophe Cerisara and C{\'{e}}cile Fougeron and Guillaume Gravier and Lori Lamel and Fran{\c{c}}ois Pellegrino and Pascal Perrier}, title = {ivector-based acoustic data selection}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {657--661}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-188}, doi = {10.21437/INTERSPEECH.2013-188}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanB13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiaoABS10, author = {Hank Liao and Christopher Alberti and Michiel Bacchiani and Olivier Siohan}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Decision tree state clustering with word and syllable features}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {2958--2961}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-28}, doi = {10.21437/INTERSPEECH.2010-28}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiaoABS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/AlbertiBBCDLMPSSS09, author = {Christopher Alberti and Michiel Bacchiani and Ari Bezman and Ciprian Chelba and Anastassia Drofa and Hank Liao and Pedro J. Moreno and Ted Power and Arnaud Sahuguet and Maria Shugrina and Olivier Siohan}, title = {An audio indexing system for election video material}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan}, pages = {4873--4876}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICASSP.2009.4960723}, doi = {10.1109/ICASSP.2009.4960723}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/AlbertiBBCDLMPSSS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/AfifyS07, author = {Mohamed Afify and Olivier Siohan}, title = {Comments on Vocal Tract Length Normalization Equals Linear Transformation in Cepstral Space}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {15}, number = {5}, pages = {1731--1732}, year = {2007}, url = {https://doi.org/10.1109/TASL.2007.896653}, doi = {10.1109/TASL.2007.896653}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/AfifyS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/RamabhadranSS07, author = {Bhuvana Ramabhadran and Olivier Siohan and Abhinav Sethy}, editor = {Sadaoki Furui and Tatsuya Kawahara}, title = {The {IBM} 2007 speech transcription system for European parliamentary speeches}, booktitle = {{IEEE} Workshop on Automatic Speech Recognition {\&} Understanding, {ASRU} 2007, Kyoto, Japan, December 9-13, 2007}, pages = {472--477}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ASRU.2007.4430158}, doi = {10.1109/ASRU.2007.4430158}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/asru/RamabhadranSS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/AfifySS07, author = {Mohamed Afify and Olivier Siohan and Ruhi Sarikaya}, title = {Gaussian Mixture Language Models for Speech Recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April 15-20, 2007}, pages = {29--32}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ICASSP.2007.367155}, doi = {10.1109/ICASSP.2007.367155}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/AfifySS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sigir/MamouRS07, author = {Jonathan Mamou and Bhuvana Ramabhadran and Olivier Siohan}, editor = {Wessel Kraaij and Arjen P. de Vries and Charles L. A. Clarke and Norbert Fuhr and Noriko Kando}, title = {Vocabulary independent spoken term detection}, booktitle = {{SIGIR} 2007: Proceedings of the 30th Annual International {ACM} {SIGIR} Conference on Research and Development in Information Retrieval, Amsterdam, The Netherlands, July 23-27, 2007}, pages = {615--622}, publisher = {{ACM}}, year = {2007}, url = {https://doi.org/10.1145/1277741.1277847}, doi = {10.1145/1277741.1277847}, timestamp = {Tue, 06 Nov 2018 11:07:23 +0100}, biburl = {https://dblp.org/rec/conf/sigir/MamouRS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ZweigSSRPMK06, author = {Geoffrey Zweig and Olivier Siohan and George Saon and Bhuvana Ramabhadran and Daniel Povey and Lidia Mangu and Brian Kingsbury}, title = {Automated Quality Monitoring in the Call Center with {ASR} and Maximum Entropy}, booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006}, pages = {589--592}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/ICASSP.2006.1660089}, doi = {10.1109/ICASSP.2006.1660089}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/ZweigSSRPMK06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RamabhadranSMZWSS06, author = {Bhuvana Ramabhadran and Olivier Siohan and Lidia Mangu and Geoffrey Zweig and Martin Westphal and Henrik Schulz and Alvaro Soneiro}, title = {The {IBM} 2006 speech transcription system for european parliamentary speeches}, booktitle = {{INTERSPEECH} 2006 - ICSLP, Ninth International Conference on Spoken Language Processing, Pittsburgh, PA, USA, September 17-21, 2006}, publisher = {{ISCA}}, year = {2006}, url = {https://doi.org/10.21437/Interspeech.2006-369}, doi = {10.21437/INTERSPEECH.2006-369}, timestamp = {Thu, 22 Jun 2023 16:42:16 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/RamabhadranSMZWSS06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mlmi/HuangWCSPLSSRP06, author = {Jing Huang and Martin Westphal and Stanley F. Chen and Olivier Siohan and Daniel Povey and Vit Libal and Alvaro Soneiro and Henrik Schulz and Thomas Ross and Gerasimos Potamianos}, editor = {Steve Renals and Samy Bengio and Jonathan G. Fiscus}, title = {The {IBM} Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings}, booktitle = {Machine Learning for Multimodal Interaction, Third International Workshop, {MLMI} 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {4299}, pages = {432--443}, publisher = {Springer}, year = {2006}, url = {https://doi.org/10.1007/11965152\_38}, doi = {10.1007/11965152\_38}, timestamp = {Fri, 10 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mlmi/HuangWCSPLSSRP06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/naacl/ZweigSSRPMK06, author = {Geoffrey Zweig and Olivier Siohan and George Saon and Bhuvana Ramabhadran and Daniel Povey and Lidia Mangu and Brian Kingsbury}, editor = {Robert C. Moore and Jeff A. Bilmes and Jennifer Chu{-}Carroll and Mark Sanderson}, title = {Automated Quality Monitoring for Call Centers using Speech and {NLP} Technologies}, booktitle = {Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings, June 4-9, 2006, New York, New York, {USA}}, publisher = {The Association for Computational Linguistics}, year = {2006}, url = {https://aclanthology.org/N06-4011/}, timestamp = {Fri, 06 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/naacl/ZweigSSRPMK06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/AfifyLJS05, author = {Mohamed Afify and Feng Liu and Hui Jiang and Olivier Siohan}, title = {A new verification-based fast-match for large vocabulary continuous speech recognition}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {13}, number = {4}, pages = {546--553}, year = {2005}, url = {https://doi.org/10.1109/TSA.2005.845809}, doi = {10.1109/TSA.2005.845809}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/AfifyLJS05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SiohanRK05, author = {Olivier Siohan and Bhuvana Ramabhadran and Brian Kingsbury}, title = {Contructing Ensembles of {ASR} Systems Using Randomized Decision Trees}, booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23, 2005}, pages = {197--200}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/ICASSP.2005.1415084}, doi = {10.1109/ICASSP.2005.1415084}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SiohanRK05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanB05, author = {Olivier Siohan and Michiel Bacchiani}, title = {Fast vocabulary-independent audio search using path-based graph indexing}, booktitle = {{INTERSPEECH} 2005 - Eurospeech, 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 4-8, 2005}, pages = {53--56}, publisher = {{ISCA}}, year = {2005}, url = {https://doi.org/10.21437/Interspeech.2005-52}, doi = {10.21437/INTERSPEECH.2005-52}, timestamp = {Thu, 22 Jun 2023 16:42:16 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanB05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/AfifyS04, author = {Mohamed Afify and Olivier Siohan}, title = {Sequential estimation with optimal forgetting for robust speech recognition}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {12}, number = {1}, pages = {19--26}, year = {2004}, url = {https://doi.org/10.1109/TSA.2003.819954}, doi = {10.1109/TSA.2003.819954}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/AfifyS04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RamabhadranSZ04, author = {Bhuvana Ramabhadran and Olivier Siohan and Geoffrey Zweig}, title = {Use of metadata to improve recognition of spontaneous speech and named entities}, booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, October 4-8, 2004}, pages = {381--384}, publisher = {{ISCA}}, year = {2004}, url = {https://doi.org/10.21437/Interspeech.2004-163}, doi = {10.21437/INTERSPEECH.2004-163}, timestamp = {Thu, 22 Jun 2023 16:42:17 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/RamabhadranSZ04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanRZ04, author = {Olivier Siohan and Bhuvana Ramabhadran and Geoffrey Zweig}, title = {Speech recognition error analysis on the English {MALACH} corpus}, booktitle = {{INTERSPEECH} 2004 - ICSLP, 8th International Conference on Spoken Language Processing, Jeju Island, Korea, October 4-8, 2004}, pages = {413--416}, publisher = {{ISCA}}, year = {2004}, url = {https://doi.org/10.21437/Interspeech.2004-171}, doi = {10.21437/INTERSPEECH.2004-171}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanRZ04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/bell/KuoSO03, author = {Hong{-}Kwang Jeff Kuo and Olivier Siohan and Joseph P. Olive}, title = {Advances in natural language call routing}, journal = {Bell Labs Tech. J.}, volume = {7}, number = {3}, pages = {155--170}, year = {2003}, url = {https://doi.org/10.1002/bltj.10040}, doi = {10.1002/BLTJ.10040}, timestamp = {Thu, 27 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/bell/KuoSO03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HilgerNSS03, author = {Florian Hilger and Hermann Ney and Olivier Siohan and Frank K. Soong}, title = {Combining neighboring filter channels to improve quantile based histogram equalization}, booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003}, pages = {640--643}, publisher = {{IEEE}}, year = {2003}, url = {https://doi.org/10.1109/ICASSP.2003.1198862}, doi = {10.1109/ICASSP.2003.1198862}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HilgerNSS03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZitouniSL03, author = {Imed Zitouni and Olivier Siohan and Chin{-}Hui Lee}, title = {Hierarchical class n-gram language models: towards better estimation of unseen events in speech recognition}, booktitle = {8th European Conference on Speech Communication and Technology, {EUROSPEECH} 2003 - {INTERSPEECH} 2003, Geneva, Switzerland, September 1-4, 2003}, pages = {237--240}, publisher = {{ISCA}}, year = {2003}, url = {https://doi.org/10.21437/Eurospeech.2003-108}, doi = {10.21437/EUROSPEECH.2003-108}, timestamp = {Thu, 22 Jun 2023 16:42:17 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZitouniSL03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/csl/SiohanML02, author = {Olivier Siohan and Tor Andr{\'{e}} Myrvoll and Chin{-}Hui Lee}, title = {Structural maximum a posteriori linear regression for fast {HMM} adaptation}, journal = {Comput. Speech Lang.}, volume = {16}, number = {1}, pages = {5--24}, year = {2002}, url = {https://doi.org/10.1006/csla.2001.0181}, doi = {10.1006/CSLA.2001.0181}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/csl/SiohanML02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/AfifySL02, author = {Mohamed Afify and Olivier Siohan and Chin{-}Hui Lee}, title = {Upper and lower bounds on the mean of noisy speech: application to minimax classification}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {10}, number = {2}, pages = {79--88}, year = {2002}, url = {https://doi.org/10.1109/89.985545}, doi = {10.1109/89.985545}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/AfifySL02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/JiangSSL02, author = {Hui Jiang and Olivier Siohan and Frank K. Soong and Chin{-}Hui Lee}, title = {A dynamic in-search discriminative training approach for large vocabulary speech recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida, {USA}}, pages = {113--116}, publisher = {{IEEE}}, year = {2002}, url = {https://doi.org/10.1109/ICASSP.2002.5743667}, doi = {10.1109/ICASSP.2002.5743667}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/JiangSSL02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LaunaySSL02, author = {Benoit Launay and Olivier Siohan and Arun C. Surendran and Chin{-}Hui Lee}, title = {Towards knowledge-based features for {HMM} based large vocabulary automatic speech recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida, {USA}}, pages = {817--820}, publisher = {{IEEE}}, year = {2002}, url = {https://doi.org/10.1109/ICASSP.2002.5743864}, doi = {10.1109/ICASSP.2002.5743864}, timestamp = {Fri, 19 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LaunaySSL02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/AfifyS02, author = {Mohamed Afify and Olivier Siohan}, title = {A discriminative training criterion and an associated {EM} learning algorithm}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2002, May 13-17 2002, Orlando, Florida, {USA}}, pages = {1065--1068}, publisher = {{IEEE}}, year = {2002}, url = {https://doi.org/10.1109/ICASSP.2002.5743979}, doi = {10.1109/ICASSP.2002.5743979}, timestamp = {Fri, 19 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/AfifyS02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChenDJLMSS02, author = {Jingdong Chen and Dimitris Dimitriadis and Hui Jiang and Qi Li and Tor Andr{\'{e}} Myrvoll and Olivier Siohan and Frank K. Soong}, editor = {John H. L. Hansen and Bryan L. Pellom}, title = {Bell labs approach to Aurora evaluation on connected digit recognition}, booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002} - {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002}, pages = {229--232}, publisher = {{ISCA}}, year = {2002}, url = {https://doi.org/10.21437/ICSLP.2002-9}, doi = {10.21437/ICSLP.2002-9}, timestamp = {Thu, 22 Jun 2023 16:42:18 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChenDJLMSS02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZitouniSKL02, author = {Imed Zitouni and Olivier Siohan and Hong{-}Kwang Jeff Kuo and Chin{-}Hui Lee}, editor = {John H. L. Hansen and Bryan L. Pellom}, title = {Backoff hierarchical class n-gram language modelling for automatic speech recognition systems}, booktitle = {7th International Conference on Spoken Language Processing, {ICSLP2002} - {INTERSPEECH} 2002, Denver, Colorado, USA, September 16-20, 2002}, pages = {885--888}, publisher = {{ISCA}}, year = {2002}, url = {https://doi.org/10.21437/ICSLP.2002-299}, doi = {10.21437/ICSLP.2002-299}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZitouniSKL02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/SiohanCL01, author = {Olivier Siohan and Cristina Chesta and Chin{-}Hui Lee}, title = {Joint maximum a posteriori adaptation of transformation and {HMM} parameters}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {9}, number = {4}, pages = {417--428}, year = {2001}, url = {https://doi.org/10.1109/89.917687}, doi = {10.1109/89.917687}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/SiohanCL01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/AfifyS01, author = {Mohamed Afify and Olivier Siohan}, title = {Sequential noise estimation with optimal forgetting for robust speech recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2001, 7-11 May, 2001, Salt Palace Convention Center, Salt Lake City, Utah, USA, Proceedings}, pages = {229--232}, publisher = {{IEEE}}, year = {2001}, url = {https://doi.org/10.1109/ICASSP.2001.940809}, doi = {10.1109/ICASSP.2001.940809}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/AfifyS01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanAAJLLLOSZ01, author = {Olivier Siohan and Akio Ando and Mohamed Afify and Hui Jiang and Chin{-}Hui Lee and Qi Li and Feng Liu and Kazuo Onoe and Frank K. Soong and Qiru Zhou}, editor = {Paul Dalsgaard and B{\o}rge Lindberg and Henrik Benner and Zheng{-}Hua Tan}, title = {A real-time Japanese broadcast news closed-captioning system}, booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September 3-7, 2001}, pages = {495--498}, publisher = {{ISCA}}, year = {2001}, url = {https://doi.org/10.21437/Eurospeech.2001-130}, doi = {10.21437/EUROSPEECH.2001-130}, timestamp = {Thu, 22 Jun 2023 16:42:18 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanAAJLLLOSZ01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiSS01, author = {Qi Li and Frank K. Soong and Olivier Siohan}, editor = {Paul Dalsgaard and B{\o}rge Lindberg and Henrik Benner and Zheng{-}Hua Tan}, title = {An auditory system-based feature for robust speech recognition}, booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September 3-7, 2001}, pages = {619--622}, publisher = {{ISCA}}, year = {2001}, url = {https://doi.org/10.21437/Eurospeech.2001-164}, doi = {10.21437/EUROSPEECH.2001-164}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiSS01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/AfifyJKLLSSS01, author = {Mohamed Afify and Hui Jiang and Filipp Korkmazskiy and Chin{-}Hui Lee and Qi Li and Olivier Siohan and Frank K. Soong and Arun C. Surendran}, editor = {Paul Dalsgaard and B{\o}rge Lindberg and Henrik Benner and Zheng{-}Hua Tan}, title = {Evaluating the Aurora connected digit recognition task - a bell labs approach}, booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September 3-7, 2001}, pages = {633--636}, publisher = {{ISCA}}, year = {2001}, url = {https://doi.org/10.21437/Eurospeech.2001-167}, doi = {10.21437/EUROSPEECH.2001-167}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/AfifyJKLLSSS01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuAJS01, author = {Feng Liu and Mohamed Afify and Hui Jiang and Olivier Siohan}, editor = {Paul Dalsgaard and B{\o}rge Lindberg and Henrik Benner and Zheng{-}Hua Tan}, title = {A new verification-based fast match approach to large vocabulary speech recognition}, booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September 3-7, 2001}, pages = {851--854}, publisher = {{ISCA}}, year = {2001}, url = {https://doi.org/10.21437/Eurospeech.2001-134}, doi = {10.21437/EUROSPEECH.2001-134}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuAJS01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/AfifySL01, author = {Mohamed Afify and Olivier Siohan and Chin{-}Hui Lee}, editor = {Paul Dalsgaard and B{\o}rge Lindberg and Henrik Benner and Zheng{-}Hua Tan}, title = {Minimax classification with parametric neighborhoods for noisy speech recognition}, booktitle = {{EUROSPEECH} 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd {INTERSPEECH} Event, Aalborg, Denmark, September 3-7, 2001}, pages = {2355--2358}, publisher = {{ISCA}}, year = {2001}, url = {https://doi.org/10.21437/Eurospeech.2001-555}, doi = {10.21437/EUROSPEECH.2001-555}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/AfifySL01.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/speech/RosenbergSP00, author = {Aaron E. Rosenberg and Olivier Siohan and Sarangarajan Parthasarathy}, title = {Small group speaker identification with common password phrases}, journal = {Speech Commun.}, volume = {31}, number = {2-3}, pages = {131--140}, year = {2000}, url = {https://doi.org/10.1016/S0167-6393(99)00074-6}, doi = {10.1016/S0167-6393(99)00074-6}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/speech/RosenbergSP00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SiohanCL00, author = {Olivier Siohan and Cristina Chesta and Chin{-}Hui Lee}, title = {Joint maximum a posteriori estimation of transformation and hidden Markov model parameters}, booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing. {ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center, Istanbul, Turkey}, pages = {965--968}, publisher = {{IEEE}}, year = {2000}, url = {https://doi.org/10.1109/ICASSP.2000.859122}, doi = {10.1109/ICASSP.2000.859122}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SiohanCL00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NiyogiPS00, author = {Partha Niyogi and Jean{-}Beno{\^{\i}}t Pierrot and Olivier Siohan}, title = {Multiple classifiers by constrained minimization}, booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing. {ICASSP} 2000, 5-9 June, 2000, Hilton Hotel and Convention Center, Istanbul, Turkey}, pages = {3462--3465}, publisher = {{IEEE}}, year = {2000}, url = {https://doi.org/10.1109/ICASSP.2000.860146}, doi = {10.1109/ICASSP.2000.860146}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/NiyogiPS00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiSS00, author = {Qi Li and Frank K. Soong and Olivier Siohan}, title = {A high-performance auditory feature for robust speech recognition}, booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP} 2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000}, pages = {51--54}, publisher = {{ISCA}}, year = {2000}, url = {https://doi.org/10.21437/ICSLP.2000-475}, doi = {10.21437/ICSLP.2000-475}, timestamp = {Thu, 22 Jun 2023 16:42:19 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiSS00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/MyrvollSLC00, author = {Tor Andr{\'{e}} Myrvoll and Olivier Siohan and Chin{-}Hui Lee and Wu Chou}, title = {Structural maximum a-posteriori linear regression for unsupervised speaker adaptation}, booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP} 2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000}, pages = {540--543}, publisher = {{ISCA}}, year = {2000}, url = {https://doi.org/10.21437/ICSLP.2000-868}, doi = {10.21437/ICSLP.2000-868}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/MyrvollSLC00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChouSML00, author = {Wu Chou and Olivier Siohan and Tor Andr{\'{e}} Myrvoll and Chin{-}Hui Lee}, title = {Extended maximum a posterior linear regression {(EMAPLR)} model adaptation for speech recognition}, booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP} 2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000}, pages = {616--619}, publisher = {{ISCA}}, year = {2000}, url = {https://doi.org/10.21437/ICSLP.2000-887}, doi = {10.21437/ICSLP.2000-887}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChouSML00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/AfifyS00, author = {Mohamed Afify and Olivier Siohan}, title = {Constrained maximum likelihood linear regression for speaker adaptation}, booktitle = {Sixth International Conference on Spoken Language Processing, {ICSLP} 2000 / {INTERSPEECH} 2000, Beijing, China, October 16-20, 2000}, pages = {861--864}, publisher = {{ISCA}}, year = {2000}, url = {https://doi.org/10.21437/ICSLP.2000-670}, doi = {10.21437/ICSLP.2000-670}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/AfifyS00.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SiohanLSL99, author = {Olivier Siohan and Chin{-}Hui Lee and Arun C. Surendran and Qi Li}, title = {Background model design for flexible and portable speaker verification systems}, booktitle = {Proceedings of the 1999 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '99, Phoenix, Arizona, USA, March 15-19, 1999}, pages = {825--828}, publisher = {{IEEE} Computer Society}, year = {1999}, url = {https://doi.org/10.1109/ICASSP.1999.759798}, doi = {10.1109/ICASSP.1999.759798}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SiohanLSL99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChestaSL99, author = {Cristina Chesta and Olivier Siohan and Chin{-}Hui Lee}, title = {Maximum a posteriori linear regression for hidden Markov model adaptation}, booktitle = {Sixth European Conference on Speech Communication and Technology, {EUROSPEECH} 1999, Budapest, Hungary, September 5-9, 1999}, pages = {211--214}, publisher = {{ISCA}}, year = {1999}, url = {https://doi.org/10.21437/Eurospeech.1999-56}, doi = {10.21437/EUROSPEECH.1999-56}, timestamp = {Sat, 01 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChestaSL99.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/RosenbergSP98, author = {Aaron E. Rosenberg and Olivier Siohan and Sarangarajan Parthasarathy}, title = {Speaker verification using minimum verification error training}, booktitle = {Proceedings of the 1998 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} '98, Seattle, Washington, USA, May 12-15, 1998}, pages = {105--108}, publisher = {{IEEE}}, year = {1998}, url = {https://doi.org/10.1109/ICASSP.1998.674378}, doi = {10.1109/ICASSP.1998.674378}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/RosenbergSP98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SiohanRP98, author = {Olivier Siohan and Aaron E. Rosenberg and Sarangarajan Parthasarathy}, title = {Speaker identification using minimum classification error training}, booktitle = {Proceedings of the 1998 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} '98, Seattle, Washington, USA, May 12-15, 1998}, pages = {109--112}, publisher = {{IEEE}}, year = {1998}, url = {https://doi.org/10.1109/ICASSP.1998.674379}, doi = {10.1109/ICASSP.1998.674379}, timestamp = {Fri, 19 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SiohanRP98.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spl/SiohanL97, author = {Olivier Siohan and Chin{-}Hui Lee}, title = {Iterative noise and channel estimation under the stochastic matching algorithm framework}, journal = {{IEEE} Signal Process. Lett.}, volume = {4}, number = {11}, pages = {304--306}, year = {1997}, url = {https://doi.org/10.1109/97.641394}, doi = {10.1109/97.641394}, timestamp = {Tue, 16 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/spl/SiohanL97.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/speech/SiohanGH96, author = {Olivier Siohan and Yifan Gong and Jean Paul Haton}, title = {Comparative experiments of several adaptation approaches to noisy speech recognition using stochastic trajectory models}, journal = {Speech Commun.}, volume = {18}, number = {4}, pages = {335--352}, year = {1996}, url = {https://doi.org/10.1016/0167-6393(96)00015-5}, doi = {10.1016/0167-6393(96)00015-5}, timestamp = {Mon, 03 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/speech/SiohanGH96.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SiohanG96, author = {Olivier Siohan and Yifan Gong}, title = {A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition}, booktitle = {1996 {IEEE} International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings, {ICASSP} '96, Atlanta, Georgia, USA, May 7-10, 1996}, pages = {471--474}, publisher = {{IEEE} Computer Society}, year = {1996}, url = {https://doi.org/10.1109/ICASSP.1996.541135}, doi = {10.1109/ICASSP.1996.541135}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SiohanG96.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@phdthesis{DBLP:phd/hal/Siohan95, author = {Olivier Siohan}, title = {Reconnaissance automatique de la parole continue en environnement bruit{\'{e}} : application {\`{a}} des mod{\`{e}}les stochastiques de trajectoires. (Continuous speech recognition in a noisy environment : application to stochastic trajectory models)}, school = {Henri Poincar{\'{e}} University, Nancy, France}, year = {1995}, url = {https://tel.archives-ouvertes.fr/tel-01748602}, timestamp = {Tue, 21 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/phd/hal/Siohan95.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Siohan95, author = {Olivier Siohan}, title = {On the robustness of linear discriminant analysis as a preprocessing step for noisy speech recognition}, booktitle = {1995 International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '95, Detroit, Michigan, USA, May 08-12, 1995}, pages = {125--128}, publisher = {{IEEE} Computer Society}, year = {1995}, url = {https://doi.org/10.1109/ICASSP.1995.479289}, doi = {10.1109/ICASSP.1995.479289}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/Siohan95.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanGH95, author = {Olivier Siohan and Yifan Gong and Jean Paul Haton}, title = {Noise adaptation using linear regression for continuous noisy speech recognition}, booktitle = {Fourth European Conference on Speech Communication and Technology, {EUROSPEECH} 1995, Madrid, Spain, September 18-21, 1995}, pages = {465--468}, publisher = {{ISCA}}, year = {1995}, url = {https://doi.org/10.21437/Eurospeech.1995-125}, doi = {10.21437/EUROSPEECH.1995-125}, timestamp = {Sat, 01 Jul 2023 23:51:24 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanGH95.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanGH94, author = {Olivier Siohan and Yifan Gong and Jean Paul Haton}, title = {A comparison of three noisy speech recognition approaches}, booktitle = {The 3rd International Conference on Spoken Language Processing, {ICSLP} 1994, Yokohama, Japan, September 18-22, 1994}, pages = {1031--1034}, publisher = {{ISCA}}, year = {1994}, url = {https://doi.org/10.21437/ICSLP.1994-272}, doi = {10.21437/ICSLP.1994-272}, timestamp = {Wed, 21 Jun 2023 17:18:06 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanGH94.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SiohanGH93, author = {Olivier Siohan and Yifan Gong and Jean Paul Haton}, title = {A Bayesian approach to phone duration adaptation for lombard speech recognition}, booktitle = {Third European Conference on Speech Communication and Technology, {EUROSPEECH} 1993, Berlin, Germany, September 22-25, 1993}, pages = {1639--1642}, publisher = {{ISCA}}, year = {1993}, url = {https://doi.org/10.21437/Eurospeech.1993-369}, doi = {10.21437/EUROSPEECH.1993-369}, timestamp = {Sat, 01 Jul 2023 23:51:24 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SiohanGH93.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GongSH92, author = {Yifan Gong and Olivier Siohan and Jean Paul Haton}, title = {Minimization of speech alignment error by iterative transformation for speaker adaptation}, booktitle = {The Second International Conference on Spoken Language Processing, {ICSLP} 1992, Banff, Alberta, Canada, October 13-16, 1992}, pages = {377--380}, publisher = {{ISCA}}, year = {1992}, url = {https://doi.org/10.21437/ICSLP.1992-108}, doi = {10.21437/ICSLP.1992-108}, timestamp = {Wed, 21 Jun 2023 17:18:06 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/GongSH92.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.